kszucs commented on a change in pull request #8088:
URL: https://github.com/apache/arrow/pull/8088#discussion_r492695285
##########
File path: python/pyarrow/tests/test_convert_builtin.py
##########
@@ -1513,6 +1519,108 @@ def test_struct_from_tuples():
pa.array([tup], type=ty)
+def test_struct_from_list_of_pairs():
+ ty = pa.struct([
+ pa.field('a', pa.int32()),
+ pa.field('b', pa.string()),
+ pa.field('c', pa.bool_())
+ ])
+ data = [
+ [('a', 5), ('b', 'foo'), ('c', True)],
+ [('a', 6), ('b', 'bar'), ('c', False)],
+ None
+ ]
+ arr = pa.array(data, type=ty)
+ assert arr.to_pylist() == [
+ {'a': 5, 'b': 'foo', 'c': True},
+ {'a': 6, 'b': 'bar', 'c': False},
+ None
+ ]
+
+ # test with duplicated field names
+ ty = pa.struct([
+ pa.field('a', pa.int32()),
+ pa.field('a', pa.string()),
+ pa.field('b', pa.bool_())
+ ])
+ data = [
+ [('a', 5), ('a', 'foo'), ('b', True)],
+ [('a', 6), ('a', 'bar'), ('b', False)],
+ ]
+ arr = pa.array(data, type=ty)
+ with pytest.raises(KeyError):
+ # TODO(kszucs): ARROW-9997
+ arr.to_pylist()
+
+ # test with empty elements
+ ty = pa.struct([
+ pa.field('a', pa.int32()),
+ pa.field('b', pa.string()),
+ pa.field('c', pa.bool_())
+ ])
+ data = [
+ [],
+ [('a', 5), ('b', 'foo'), ('c', True)],
+ [('a', 2), ('b', 'baz')],
+ [('a', 1), ('b', 'bar'), ('c', False), ('d', 'julia')],
Review comment:
> Since the _order_ matters when constructing from pairs (based on the
test below), I would personally expect additional elements would also not be
allowed (BTW, what actually happens if the additional element is not in the
last position? Maybe add a test for that as well?).
It will raise since the key field equality is checked explicitly. It also
supports converting less elements than the number of fields.
##########
File path: python/pyarrow/tests/test_convert_builtin.py
##########
@@ -1513,6 +1519,108 @@ def test_struct_from_tuples():
pa.array([tup], type=ty)
+def test_struct_from_list_of_pairs():
+ ty = pa.struct([
+ pa.field('a', pa.int32()),
+ pa.field('b', pa.string()),
+ pa.field('c', pa.bool_())
+ ])
+ data = [
+ [('a', 5), ('b', 'foo'), ('c', True)],
+ [('a', 6), ('b', 'bar'), ('c', False)],
+ None
+ ]
+ arr = pa.array(data, type=ty)
+ assert arr.to_pylist() == [
+ {'a': 5, 'b': 'foo', 'c': True},
+ {'a': 6, 'b': 'bar', 'c': False},
+ None
+ ]
+
+ # test with duplicated field names
+ ty = pa.struct([
+ pa.field('a', pa.int32()),
+ pa.field('a', pa.string()),
+ pa.field('b', pa.bool_())
+ ])
+ data = [
+ [('a', 5), ('a', 'foo'), ('b', True)],
+ [('a', 6), ('a', 'bar'), ('b', False)],
+ ]
+ arr = pa.array(data, type=ty)
+ with pytest.raises(KeyError):
+ # TODO(kszucs): ARROW-9997
+ arr.to_pylist()
+
+ # test with empty elements
+ ty = pa.struct([
+ pa.field('a', pa.int32()),
+ pa.field('b', pa.string()),
+ pa.field('c', pa.bool_())
+ ])
+ data = [
+ [],
+ [('a', 5), ('b', 'foo'), ('c', True)],
+ [('a', 2), ('b', 'baz')],
+ [('a', 1), ('b', 'bar'), ('c', False), ('d', 'julia')],
Review comment:
> Since the _order_ matters when constructing from pairs (based on the
test below), I would personally expect additional elements would also not be
allowed (BTW, what actually happens if the additional element is not in the
last position? Maybe add a test for that as well?).
It will raise since the key field equality is checked explicitly. It also
supports converting less elements than the number of fields.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
